Authors

Shuo Zhang

Document Type

Dissertation

Disciplines

2.2 ELECTRICAL, ELECTRONIC, INFORMATION ENGINEERING

Publication Details

Thesis presented for the award of Doctor of Philosophy, Technological University of Dublin, 2023.

Abstract

The operation and maintenance (O&M) issues of wind turbines (WTs) are challenging because unplanned maintenance, caused by sudden component failures, can bring about durable downtimes and significant revenue losses. It is important to carry out effective fault diagnostics and prognostics schemes under the rapid development of wind power generation. Hence, Condition Monitoring (CM) solutions focus on measurements and detections of high-risk WT components, which could result in high failure rates and long downtimes. Machine Learning (ML) models have been commonly applied in CM to allocate imminent indications of failure or degradation for curtailing the O&M costs of WTs. By way of using supervisory control and data acquisition (SCADA) or simulation data, many ML models have been predominantly developed with supervised classification models to categorize the fault types and regression models to predict the continuous outputs and detect the anomaly. In this thesis, the studies on WT, including fault diagnostics and prognostics, curve fitting, and performance monitoring and forecasting, are addressed through ML and Deep Learning (DL) based CM schemes.

DOI

https://doi.org/10.21427/05yg-cn52

Creative Commons License

Creative Commons Attribution-No Derivative Works 4.0 International License
This work is licensed under a Creative Commons Attribution-No Derivative Works 4.0 International License.


Share

COinS